Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 6-RES-JB
    6. 6833
    Prev
    Next
    INDEX
    Explanations

    names of individuals and financial institutions related to Islamic finance

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.18
    0.7%
    1703
    +0.09
    0.3%
    1120
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1703
    +0.18
    0.05
    1120
    +0.09
    0.02
    1290
    +0.08
    0.06
    Negative Logits
    <bos>
    -2.64
    ⓧ
    -1.00
    /***
    
    -0.69
    <?
    -0.67
    /*!
    
    -0.60
    ngOn
    -0.58
    <?
    
    -0.57
    
    
    -0.54
     duomen
    -0.54
     sclero
    -0.52
    POSITIVE LOGITS
     aussitôt
    1.05
     librement
    0.91
     philanth
    0.89
     spécialement
    0.89
     McLaugh
    0.88
     ladite
    0.88
     quoique
    0.87
     habituellement
    0.86
     constamment
    0.86
     définitivement
    0.85
    Activations Density 0.458%

    No Known Activations